GHSA-29R9-67VG-QJ56
Vulnerability from github – Published: 2026-10-08 16:43 – Updated: 2026-10-08 16:43Summary
PraisonAI gates dangerous tools (file writes, deletes, shell/code execution) behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silently reused for all later invocations of that tool with arbitrary, unreviewed arguments.
Root cause
ApprovalRegistry.is_already_approved (src/praisonai-agents/praisonaiagents/approval/registry.py, around line 181) returns True whenever the tool name is present in a per-run context set. The cache is keyed on tool name only — arguments are not part of the key.
approve_sync / approve_async (around lines 224-226 / 278-279) short-circuit on that cache before the approval backend is consulted.
clear_approved (around lines 186-187) is the only routine that clears the cache, but it is never invoked in the shipped library (only in tests). The cache persists for the entire agent run and is inherited by child tasks via contextvars.
Critical-tier tools (execute_command, execute_code) are exempt from the cache. But high-risk tools like write_file are not.
Proof of concept
from praisonaiagents.approval.registry import ApprovalRegistry
from praisonaiagents.approval.protocols import ApprovalDecision, ApprovalRequest
class CountingBackend:
def __init__(self): self.prompts = []
def request_approval_sync(self, request):
self.prompts.append((request.tool_name, dict(request.arguments)))
return ApprovalDecision(approved=True, reason="human approved")
backend = CountingBackend()
reg = ApprovalRegistry()
reg.set_backend(backend)
reg.add_requirement("write_file", "high")
d1 = reg.approve_sync("agent", "write_file", {"path": "/tmp/safe.txt", "content": "hi"})
# Human prompted — approves a benign write
d2 = reg.approve_sync("agent", "write_file", {"path": "/etc/crontab", "content": "* * * * * root evil"})
# NO prompt — auto-approved from cache
assert len(backend.prompts) == 1
assert d2.reason == "Already approved in context"
Negative control: execute_command (critical) re-prompts on every call — 2 prompts for 2 calls.
Impact
A write_file approval for a benign path authorizes every later write_file call in the session with arbitrary arguments. A model steered by malicious input can write to sensitive locations with no further human prompt.
Suggested fix
- Include arguments in the approval cache key, or re-prompt on argument change.
- Expire the cache per-call or per-turn.
- Do not inherit the cache into child tasks.
{
"affected": [
{
"database_specific": {
"last_known_affected_version_range": "\u003c= 1.6.77"
},
"package": {
"ecosystem": "PyPI",
"name": "praisonaiagents"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "1.6.78"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-60087"
],
"database_specific": {
"cwe_ids": [
"CWE-863"
],
"github_reviewed": true,
"github_reviewed_at": "2026-10-08T16:43:45Z",
"nvd_published_at": "2026-07-15T17:16:52Z",
"severity": "MODERATE"
},
"details": "## Summary\n\nPraisonAI gates dangerous tools (file writes, deletes, shell/code execution) behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silently reused for all later invocations of that tool with arbitrary, unreviewed arguments.\n\n## Root cause\n\n`ApprovalRegistry.is_already_approved` (`src/praisonai-agents/praisonaiagents/approval/registry.py`, around line 181) returns `True` whenever the tool name is present in a per-run context set. The cache is keyed on tool name only \u2014 arguments are not part of the key.\n\n`approve_sync` / `approve_async` (around lines 224-226 / 278-279) short-circuit on that cache before the approval backend is consulted.\n\n`clear_approved` (around lines 186-187) is the only routine that clears the cache, but it is never invoked in the shipped library (only in tests). The cache persists for the entire agent run and is inherited by child tasks via `contextvars`.\n\nCritical-tier tools (`execute_command`, `execute_code`) are exempt from the cache. But high-risk tools like `write_file` are not.\n\n## Proof of concept\n\n```python\nfrom praisonaiagents.approval.registry import ApprovalRegistry\nfrom praisonaiagents.approval.protocols import ApprovalDecision, ApprovalRequest\n\nclass CountingBackend:\n def __init__(self): self.prompts = []\n def request_approval_sync(self, request):\n self.prompts.append((request.tool_name, dict(request.arguments)))\n return ApprovalDecision(approved=True, reason=\"human approved\")\n\nbackend = CountingBackend()\nreg = ApprovalRegistry()\nreg.set_backend(backend)\nreg.add_requirement(\"write_file\", \"high\")\n\nd1 = reg.approve_sync(\"agent\", \"write_file\", {\"path\": \"/tmp/safe.txt\", \"content\": \"hi\"})\n# Human prompted \u2014 approves a benign write\n\nd2 = reg.approve_sync(\"agent\", \"write_file\", {\"path\": \"/etc/crontab\", \"content\": \"* * * * * root evil\"})\n# NO prompt \u2014 auto-approved from cache\n\nassert len(backend.prompts) == 1\nassert d2.reason == \"Already approved in context\"\n```\n\nNegative control: `execute_command` (critical) re-prompts on every call \u2014 2 prompts for 2 calls.\n\n## Impact\n\nA `write_file` approval for a benign path authorizes every later `write_file` call in the session with arbitrary arguments. A model steered by malicious input can write to sensitive locations with no further human prompt.\n\n## Suggested fix\n\n- Include arguments in the approval cache key, or re-prompt on argument change.\n- Expire the cache per-call or per-turn.\n- Do not inherit the cache into child tasks.",
"id": "GHSA-29r9-67vg-qj56",
"modified": "2026-10-08T16:43:45Z",
"published": "2026-10-08T16:43:45Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-29r9-67vg-qj56"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-60087"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-62164"
},
{
"type": "PACKAGE",
"url": "https://github.com/MervinPraison/PraisonAI"
},
{
"type": "WEB",
"url": "https://www.vulncheck.com/advisories/praisonai-before-tool-approval-cache-bypass"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:L",
"type": "CVSS_V3"
}
],
"summary": "PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments"
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
Loading timeline…
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.